© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 954
    Prev
    Next
    INDEX
    Explanations

    the word "last" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -1.20
    حوالہ
    -0.88
     Uniti
    -0.88
     sẻ
    -0.88
     BorderSide
    -0.85
    KommentareTeilen
    -0.84
    yczą
    -0.83
     ApJ
    -0.83
     Athenians
    -0.83
     Mercure
    -0.80
    POSITIVE LOGITS
     last
    2.51
    last
    2.26
     Last
    2.16
    Last
    2.14
     LAST
    2.12
    LAST
    2.01
     letzten
    1.59
    setLast
    1.55
     último
    1.52
     dernière
    1.50
    Activations Density 0.055%

    No Known Activations